Daily Papers of 2023-09-27

1. QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models 46 upvotes, #1 of 2023-09-27
2. LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models 43 upvotes, #2 of 2023-09-27
3. VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning 35 upvotes, #3 of 2023-09-27
4. Aligning Large Multimodal Models with Factually Augmented RLHF 32 upvotes, #4 of 2023-09-27
5. DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models 22 upvotes, #5 of 2023-09-27
6. Efficient Post-training Quantization with FP8 Formats 11 upvotes, #6 of 2023-09-27
7. Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models 7 upvotes, #7 of 2023-09-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.